On Mon, 7 Apr 2014, Mike Galbraith wrote:
On Mon, 2014-04-07 at 10:16 +0200, Peter Zijlstra wrote:On Mon, Apr 07, 2014 at 09:30:30AM +0200, Mike Galbraith wrote:- double_lock(&my_grp->lock, &grp->lock); + BUG_ON(irqs_disabled()); + double_lock_irq(&my_grp->lock, &grp->lock);So either make this: local_irq_disable(); double_lock(); orfor (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { my_grp->faults[i] -= p->numa_faults_memory[i]; @@ -1692,6 +1693,7 @@ static void task_numa_group(struct task_ spin_unlock(&my_grp->lock); spin_unlock(&grp->lock); + local_irq_enable();use: spin_unlock() spin_unlock_irq() or so, but this imbalance is making my itch :-)sched, numa: fix task_numa_free() lockdep splat Sasha reports that lockdep claims 156654f491dd8d52687a5fbe1637f472a52ce75b made numa_group.lock interrupt unsafe. While I don't see how that could be given the commit in question moved task_numa_free() from one irq enabled region to another, the below does make both gripes and lockups upon gripe with numa=fake=4 go away.
Hi I Am hitting this bug quite frequently. I do not see the problem after applying this patch. Thanks Tested-by: Govindarajulu Varadarajan <govindx7c6@xxxxxxxxx>
Reported-by: Sasha Levin <sasha.levin@xxxxxxxxxx>
Signed-off-by: Mike Galbraith <bitbucket@xxxxxxxxx>
---
kernel/sched/fair.c | 13 +++++++------
kernel/sched/sched.h | 9 +++++++++
2 files changed, 16 insertions(+), 6 deletions(-)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1497,7 +1497,7 @@ static void task_numa_placement(struct t
/* If the task is part of a group prevent parallel updates to group stats */
if (p->numa_group) {
group_lock = &p->numa_group->lock;
- spin_lock(group_lock);
+ spin_lock_irq(group_lock);
}
/* Find the node with the highest number of faults */
@@ -1572,7 +1572,7 @@ static void task_numa_placement(struct t
}
}
- spin_unlock(group_lock);
+ spin_unlock_irq(group_lock);
}
/* Preferred node as the node with the most faults */
@@ -1677,7 +1677,8 @@ static void task_numa_group(struct task_
if (!join)
return;
- double_lock(&my_grp->lock, &grp->lock);
+ BUG_ON(irqs_disabled());
+ double_lock_irq(&my_grp->lock, &grp->lock);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
my_grp->faults[i] -= p->numa_faults_memory[i];
@@ -1691,7 +1692,7 @@ static void task_numa_group(struct task_
grp->nr_tasks++;
spin_unlock(&my_grp->lock);
- spin_unlock(&grp->lock);
+ spin_unlock_irq(&grp->lock);
rcu_assign_pointer(p->numa_group, grp);
@@ -1710,14 +1711,14 @@ void task_numa_free(struct task_struct *
void *numa_faults = p->numa_faults_memory;
if (grp) {
- spin_lock(&grp->lock);
+ spin_lock_irq(&grp->lock);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
grp->faults[i] -= p->numa_faults_memory[i];
grp->total_faults -= p->total_numa_faults;
list_del(&p->numa_entry);
grp->nr_tasks--;
- spin_unlock(&grp->lock);
+ spin_unlock_irq(&grp->lock);
rcu_assign_pointer(p->numa_group, NULL);
put_numa_group(grp);
}
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1388,6 +1388,15 @@ static inline void double_lock(spinlock_
spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}
+static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2)
+{
+ if (l1 > l2)
+ swap(l1, l2);
+
+ spin_lock_irq(l1);
+ spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
{
if (l1 > l2)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
-- To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
|